Alternatives and similar repositories for ParaAttention

Users that are interested in ParaAttention are comparing it to the libraries listed below

• mit-han-lab / radial-attention
  [NeurIPS 2025] Radial Attention: O(nlogn) Sparse Attention with Energy Decay for Long Video Generation
  ☆571Updated 2 months ago
• nunchaku-tech / deepcompressor
  Model Compression Toolbox for Large Language Models and Diffusion Models
  ☆730Updated 4 months ago
• sayakpaul / diffusers-torchao
  End-to-end recipes for optimizing diffusion models with torchao and diffusers (inference and FP8 training).
  ☆388Updated this week
• Shenyi-Z / TaylorSeer
  [ICCV2025] From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
  ☆354Updated 5 months ago
• vipshop / cache-dit
  🤗A PyTorch-native and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for DiTs.
  ☆861Updated this week
• Zehong-Ma / MagCache
  The official code for NeurIPS 2025 "MagCache: Fast Video Generation with Magnitude-Aware Cache"
  ☆248Updated last month
• MingXiangL / Teacache-xDiT
  Combining Teacache with xDiT to Accelerate Visual Generation Models
  ☆32Updated 8 months ago
• Vchitect / FasterCache
  [ICLR 2025] FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality
  ☆257Updated last year
• czg1225 / AsyncDiff
  [NeurIPS 2024] AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
  ☆211Updated 3 months ago
• svg-project / Sparse-VideoGen
  [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention
  ☆616Updated last month
• mit-han-lab / distrifuser
  [CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
  ☆716Updated last year
• ali-vilab / TeaCache
  Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model
  ☆1,218Updated 7 months ago
• aredden / flux-fp8-api
  Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x fast…
  ☆285Updated last year
• modelscope / DiffSynth-Engine
  ☆341Updated this week
• huggingface / flux-fast
  Making Flux go brrr on GPUs.
  ☆159Updated 5 months ago
• thu-ml / SpargeAttn
  [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.
  ☆883Updated last week
• xdit-project / DistVAE
  A parallelism VAE avoids OOM for high resolution image generation
  ☆84Updated 5 months ago
• thu-nics / DiTFastAttn
  ☆189Updated 11 months ago
• Chenglin-Yang / 1.58bit.flux
  ☆282Updated last year
• TMElyralab / lyraDiff
  An out-of-the-box inference acceleration engine for Diffusion and DiT models
  ☆60Updated 9 months ago
• microsoft / RAS
  An open-source implementation of Regional Adaptive Sampling (RAS), a novel diffusion model sampling strategy that introduces regional var…
  ☆149Updated 6 months ago
• G-U-N / Phased-Consistency-Model
  [NeurIPS 2024] Boosting the performance of consistency models with PCM!
  ☆509Updated last year
• Shenyi-Z / ToCa
  [ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching
  ☆202Updated 9 months ago
• bebebe666 / OptimalSteps
  Official PyTorch Implementation of "Optimal Stepsize for Diffusion Sampling".
  ☆193Updated 8 months ago
• GoatWu / Self-Forcing-Plus
  Unofficial extension implementation of Self-Forcing to support I2V && 14B training.
  ☆317Updated 3 months ago
• SandAI-org / MagiAttention
  A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
  ☆598Updated last week
• lodestone-rock / flow
  ☆167Updated this week
• FlyMyAI / flymyai-lora-trainer
  Qwen-Image text to image lora trainer
  ☆672Updated 3 weeks ago
• NUS-HPC-AI-Lab / Enhance-A-Video
  Enhance-A-Video: Better Generated Video for Free
  ☆592Updated 9 months ago
• HaozheLiu-ST / T-GATE
  T-GATE: Temporally Gating Attention to Accelerate Diffusion Model for Free!
  ☆415Updated 10 months ago